A method for recognizing handwritten text is disclosed. The method comprises receiving data comprising a sequence of ink points; applying the received data to a neural network-based sequence classifier trained with a Connectionist Temporal Classification (CTC) output layer using forced alignment to generate an output; generating a character hypothesis as a portion of the sequence of ink points; applying the character hypothesis to a character classifier to obtain a first probability corresponding to the probability that the character hypothesis includes the given character; processing the output of the CTC output layer to determine a second probability corresponding to the probability that the given character is observed within the character hypothesis; and combining the first probability and the second probability to obtain a combined probability corresponding to the probability that the character hypothesis includes the given character.

Methods and supporting systems for representing and searching characters, comprising: obtaining an image of the character, labelling a structure of the character by defining a plurality of nodes and a plurality of edges on the character in the image, and generating a representation of the character by extracting a set of two-dimensional coordinates to represent the plurality of nodes and by extracting a matrix to represent the plurality of edges, and providing the representation in a searchable database.

Herein is machine learning for anomalous graph detection based on graph embedding, shuffling, comparison, and unsupervised training techniques that can characterize an unfamiliar graph. In an embodiment, a computer obtains many known vectors that respectively represent known graphs. A new vector is generated that represents a new graph that contains multiple vertices. The new vector may contain an arithmetic aggregation of vertex vectors that respectively represent multiple vertices and/or a vector that represents a virtual vertex that is connected to the multiple vertices by respective virtual edges. In the many known vectors, some similar vectors that are similar to the new vector are identified. The new graph is automatically characterized based on a subset of the known graphs that the similar vectors represent.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

A system and a method for training an inference model using a computing device. The method includes: providing a text-to-vector converter; providing the inference model and pre-training the inference model using labeled fashion entries; providing non-labeled fashion entries; separating each of the non-labeled fashion entries into a target image and target text; converting the target text into a category vector and an attribute vector using the text-to-vector converter; processing the target image using the inference model to obtain processed target image and target image label; comparing the category vector to the target image label; when the category vector matches the target image label, updating the target image label based on the category vector and the attribute vector to obtain updated label; and retraining the inference model using the processed target image and the updated label.

A computer system is provided. The computer system includes a memory and at least one processor coupled to the memory. The at least one processor is configured to scan session data representative of operation of a user interface comprising a plurality of user interface elements; detect, at a point in the session data, at least one changed element within the plurality of user interface elements; classify, in response to detecting the at least one changed element, the at least one changed element as either indicating or not indicating an error; store an association between the error and the point in the session data; and provide access to the point in the session data via the association.

An apparatus includes a memory and processor. The memory stores OCR and NLP algorithms. The processor receives an image of a physical document page and executes the OCR algorithm to convert the image into text. The processor identifies errors in the text, which are associated with noise in the image. The processor generates a feature vector that includes features obtained by executing the NLP algorithm on the text, and features associated with the identified errors in the text. The processor uses the feature vector to assign the image to a document category. Documents assigned to the document category share one or more characteristics, and the feature vector is associated with a probability greater than a threshold that the physical document associated with the image includes those characteristics. The processor then stores the image in a database as a page of an electronic document belonging to the assigned document category.

A method and system is provided for determining the denomination and related data for a currency item using a personal computing device, such as a mobile phone. The device includes or is connected to an image capture device that is preferably a digital video camera. At least one image of a target currency item is captured then processed for image quality. A further processing of the image includes a coordinate mapping. A comparison is made between individual pixels of the processed image based on the assigned coordinate mapping with a database of reference currency images to determine the currency denomination. Additional processing of the currency image provides the date and other data regarding the target currency item. A market value for the target currency item is identified by reference to a valuation database using the data determined for the currency item.

Method, computer readable medium, and apparatus of recognizing character zone in a digital document. In an embodiment, the method includes classifying a segment of the digital document as including text, calculating at least one parameter value associated with the classified segment of the digital document, determining, based on the calculated at least one parameter value, a zonal parameter value, classifying the segment of the digital document as a handwritten text zone or as a printed text zone based on the determined zonal parameter value and a threshold value, the threshold value being based on a selection of an intersection of a handwritten text distribution profile and a printed text distribution profile, each of the handwritten text distribution profile and the printed text distribution profile being associated with a zonal parameter corresponding to the determined zonal parameter value, and generating, based on the classifying, a modified version of the digital document.

In some embodiments, apparatuses and methods are provided herein useful to detecting text in images. In some embodiments, a system for detecting text in images comprises a database configured to store images and a control circuit configured to retrieve an image, generate, based on the image, a collection of augmented images, detect characters in each of the augmented images, generate bounding boxes for the characters in each of augmented images, recognize the characters in each of the augmented images, select, based on the recognition of the characters in each of the augmented images, candidate characters, wherein the candidate characters are selected based on consistency of the recognition of the characters in each of the augmented images, detect, for the image, a color associated with the characters, and store, in the database, the image, the candidate characters, and the color associated with the characters.